Discounted AI API pricing for GPT, Claude, Gemini and Grok.
Outrun is a prepaid API for 80 AI models, including GPT, Claude, Gemini and Grok. The 10 flagship models below cost 16% to 95% less per token on Outrun than at the maker's own list price.
$0.10free API credit for eligible new accounts.
- Grok 4.795%lower$0.26
list price $6.00per 1M output tokens vs xAI list price - GPT-6.1 Sol94%lower$0.59
list price $10.00per 1M output tokens vs OpenAI list price - DeepSeek V4.1 Flash 101786%lower$0.16
list price $1.20per 1M output tokens vs DeepSeek list price - Claude Sonnet 5.575%lower$2.45
list price $10.00per 1M output tokens vs Anthropic list price - Gemini 3.8 Flash58%lower$1.58
list price $3.75per 1M output tokens vs Google list price
How do Outrun prices compare with list prices?
Each model below costs 16% to 95% less per token on Outrun. Every Outrun rate is compared with the standard pay-as-you-go price on the maker's own pricing page. Batch, off-peak and volume discounts are left out, and where a model has context tiers both sides use the short-context rate.
| Model | Outrun | List price | Output saving | Source |
|---|---|---|---|---|
Grok 4.7grok-4.7Outrun rate for prompts up to 200k tokens. | $0.09/$0.26 | $2.00/$6.00 | 95% lower | xAI |
GPT-6.1 Solgpt-6.1-solOpenAI standard tier, short-context rate; Outrun rate for prompts up to 272k tokens. | $0.12/$0.59 | $2.00/$10.00 | 94% lower | OpenAI |
GPT-6 Astragpt-6-astraOpenAI standard tier, short-context rate; Outrun rate for prompts up to 272k tokens. | $0.59/$2.94 | $10.00/$50.00 | 94% lower | OpenAI |
Claude Sonnet 5.5claude-sonnet-5-5Launch pricingAnthropic base token rates. Outrun shows this model with launch pricing. | $0.49/$2.45 | $2.00/$10.00 | 75% lower | Anthropic |
DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017Provider ZDRDeepSeek lists deepseek-flash as model version DeepSeek-V4.1-Flash-1017. Peak rate (cache miss); off-peak is half of this. | $0.08/$0.16 | $0.30/$1.20 | 86% lower | DeepSeek |
Gemini 3.8 Flashgemini-3.8-flashGoogle paid-tier rate through December 31, 2026; Google lists $1.50 in and $7.50 out from January 1, 2027. | $0.32/$1.58 | $0.75/$3.75 | 58% lower | |
GLM-5.3glm-5.3 | $0.66/$2.06 | $1.40/$4.40 | 53% lower | Z.ai |
Claude Opus 5.5claude-opus-5-5Launch pricingAnthropic base token rates. Outrun shows this model with launch pricing. | $2.24/$11.20 | $4.00/$20.00 | 44% lower | Anthropic |
Claude Fable 5.1claude-fable-5-1Anthropic base token rates. | $6.30/$31.50 | $10.00/$50.00 | 37% lower | Anthropic |
GLM-5.3 Flashglm-5.3-flash | $0.12/$0.42 | $0.15/$0.50 | 16% lower | Z.ai |
Every rate is for the exact model named. Outrun sends each request to the model ID you choose and never reroutes it to a cheaper model.
List prices were read from the OpenAI, Anthropic, Google, xAI, Z.ai and DeepSeek pricing pages on October 22, 2026 and can change at any time.
Every model and price
All 80 models in the Outrun catalog, with the rate for each tier. Text rates are per 1M tokens. The uncensored models page explains the uncensored and abliterated models, and the DeepSeek, GLM-5.3, GPT and Claude API guides compare every version of those models.
Showing all 80 models
| Model | Input | Output | Cached input |
|---|---|---|---|
| OpenAI GPTGuide | |||
GPT-5.6 Solgpt-5.6-solup to 272k tokens | $0.30 | $1.77 | $0.03 |
| GPT-5.6 Sol, over 272k tokens | $0.59 | $2.65 | $0.06 |
GPT-5.6 Terragpt-5.6-terraup to 272k tokens | $0.12 | $0.71 | $0.02 |
| GPT-5.6 Terra, over 272k tokens | $0.24 | $1.06 | $0.03 |
GPT-6 Astragpt-6-astraup to 272k tokens | $0.59 | $2.94 | $0.06 |
| GPT-6 Astra, over 272k tokens | $1.18 | $4.41 | $0.12 |
GPT-6 Solgpt-6-solup to 272k tokens | $0.12 | $0.59 | $0.02 |
| GPT-6 Sol, over 272k tokens | $0.24 | $0.89 | $0.03 |
GPT-6.1 Solgpt-6.1-solup to 272k tokens | $0.12 | $0.59 | $0.01 |
| GPT-6.1 Sol, over 272k tokens | $0.24 | $0.89 | $0.02 |
| Anthropic ClaudeGuide | |||
Claude Fable 5claude-fable-5Launch pricing | $5.60 | $28.00 | $0.56 |
Claude Fable 5.1claude-fable-5-1 | $6.30 | $31.50 | $0.16 |
Claude Opus 5claude-opus-5 | $3.15 | $15.75 | $0.32 |
Claude Opus 5.5claude-opus-5-5Launch pricing | $2.24 | $11.20 | $0.12 |
Claude Sonnet 5claude-sonnet-5Launch pricing | $1.12 | $5.60 | $0.12 |
Claude Sonnet 5.5claude-sonnet-5-5Launch pricing | $0.49 | $2.45 | $0.05 |
| Google Gemini | |||
Gemini 3.1 Pro Previewgemini-3.1-pro-previewup to 200k tokens | $1.26 | $7.56 | $0.13 |
| Gemini 3.1 Pro Preview, over 200k tokens | $2.52 | $11.34 | $0.26 |
Gemini 3.7 Flashgemini-3.7-flash | $0.95 | $4.73 | $0.10 |
Gemini 3.8 Flashgemini-3.8-flash | $0.32 | $1.58 | $0.04 |
Gemini 4 Argongemini-4-argon | $1.20 | $6.00 | $0.12 |
| xAI Grok | |||
Grok 4.7grok-4.7up to 200k tokens | $0.09 | $0.26 | $0.03 |
| Grok 4.7, over 200k tokens | $0.17 | $0.51 | $0.05 |
| DeepSeekGuide | |||
DeepSeek V4 Flashdeepseek-v4-flash | $0.45 | $1.35 | $0.02 |
DeepSeek V4 Prodeepseek-v4-pro | $1.35 | $4.05 | $0.05 |
DeepSeek V4.1 Flashdeepseek-v4.1-flash | $0.30 | $1.20 | $0.01 |
DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017Provider ZDR | $0.08 | $0.16 | $0.02 |
DeepSeek V4.1 Flash 1017 (3)deepseek-v4.1-flash-1017-3 | $0.20 | $1.00 | $0.01 |
| Zhipu GLMGuide | |||
GLM-5.3glm-5.3 | $0.66 | $2.06 | $0.13 |
GLM-5.3 Flashglm-5.3-flash | $0.12 | $0.42 | $0.04 |
GLM-5.3 Flash Cybersecurityglm-5.3-flash-cybersecurity | $0.30 | $1.00 | $0.15 |
| Moonshot Kimi | |||
Kimi K3kimi-k3 | $1.80 | $9.00 | $0.18 |
| MiniMax | |||
MiniMax M3MiniMax-M3 | $0.18 | $0.72 | $0.04 |
MiniMax M3.1 Flashminimax-m3.1-flash | $0.09 | $0.36 | $0.01 |
| Inception | |||
Mercury 3mercury-3 | $0.20 | $0.70 | $0.02 |
| Model | Input | Output | Cached input |
|---|---|---|---|
Apex Flash 1 Abliteratedglm-5.3-flash-apex-abliterated | $0.30 | $1.00 | $0.15 |
DeepSeek V4 Pro Uncensoreddeepseek-v4-pro-uncensored | $0.50 | $0.50 | $0.10 |
DeepSeek V4.1 Flash Abliterateddeepseek-v4.1-flash-abliterated | $2.10 | $2.10 | $0.36 |
DeepSeek V4.1 Flash Abliterated (2)deepseek-v4.1-flash-abliterated-2 | $0.70 | $0.70 | $0.12 |
GLM-5.3 Abliteratedglm-5.3-abliterated | $1.40 | $1.40 | $0.40 |
GLM-5.3 Abliterated (2)glm-5.3-abliterated-2 | $4.50 | $4.50 | $1.32 |
GLM-5.3 Flash Abliteratedglm-5.3-flash-abliterated | $0.40 | $0.40 | $0.10 |
GLM-5.3 Flash Abliterated (2)glm-5.3-flash-abliterated-2 | $1.32 | $1.32 | $0.36 |
GLM-5.3 Flash Code Uncensoredglm-5.3-flash-code-uncensored | $12.00 | $12.00 | $12.00 |
GLM-5.3 Flash Uncensoredglm-5.3-flash-uncensored | $0.10 | $0.10 | $0.01 |
GLM-5.3 Flash Uncensored (2)glm-5.3-flash-uncensored-2 | $0.17 | $0.17 | $0.02 |
GLM-5.3 Flash Uncensored (3)glm-5.3-flash-uncensored-3 | $0.40 | $1.60 | $0.14 |
GLM-5.3 Uncensoredglm-5.3-uncensored | $0.20 | $0.20 | $0.06 |
GLM-5.3 Uncensored (2)glm-5.3-uncensored-2 | $0.35 | $0.35 | $0.10 |
GLM-5.3 Uncensored (3)glm-5.3-uncensored-3 | $2.50 | $4.50 | $0.60 |
GPT OSS 120B Uncensoredgpt-oss-120b-uncensored | $0.22 | $1.46 | $0.22 |
Hermes 4 405Bhermes-4-405b-uncensored | $1.80 | $7.20 | $1.80 |
Kimi K2.6 Uncensoredkimi-k2.6-uncensored | $2.34 | $14.68 | $0.59 |
MiMo V2.6 Flash Abliteratedmimo-v2.6-flash-abliterated | $1.00 | $3.00 | $0.55 |
MiMo V2.6 Flash Uncensoredmimo-v2.6-flash-uncensored | $1.00 | $3.00 | $0.40 |
MiMo V2.6 Flash Uncensored Thinkingmimo-v2.6-flash-uncensored-thinking | $1.00 | $3.00 | $0.40 |
MiniMax M3 Uncensoredminimax-m3-uncensored | $1.50 | $8.00 | $0.38 |
Nemotron 3 Ultra 550B Uncensorednemotron-3-ultra-550b-a55b-uncensored | $1.69 | $9.90 | $0.43 |
Outrun Red Team Flashoutrun-redteam-flash | $1.35 | $4.50 | $0.24 |
Outrun Red Team Prooutrun-redteam-pro | $2.25 | $9.00 | $0.64 |
| Model | Per image |
|---|---|
GPT Image 2gpt-image-2 | $0.06 |
Grok Imagine Imagegrok-imagine-image | $0.06 |
Nano Banana / Gemini 3.1 Flash Imagegemini-3.1-flash-image | $0.03 |
Nano Banana Pro / Gemini 3 Pro Imagegemini-3-pro-image | $0.04 |
Anime Image Uncensoredanime-image-uncensoredUncensored | $0.04 |
Chroma Uncensoredchroma-uncensoredUncensored | $0.01 |
Lustify SDXL Uncensoredlustify-sdxl-uncensoredUncensored | $0.02 |
Qwen Image 2.1 Uncensoredqwen-image-2.1-uncensoredUncensored1K | $0.08 |
| Qwen Image 2.1 Uncensored, 2K | $0.40 |
Seedream 5.0 Lite Edit Uncensoredseedream-5.0-lite-edit-uncensoredUncensored | $0.07 |
Vision Image Uncensoredvision-image-uncensoredUncensored | $0.01 |
Vision Pro Image Uncensoredvision-pro-image-uncensoredUncensored | $0.09 |
| Model | Per second |
|---|---|
Gemini Omni Flashgemini-omni-flash | $0.06 |
Grok Imagine Videogrok-imagine-video | $0.03 |
Grok Imagine Video 1.5 1080pgrok-imagine-video-1.5-1080p | $0.09 |
MiniMax H3MiniMax-H3 | $0.06 |
Seedance 2.0 1080pseedance-2.0-1080p | $0.42 |
Seedance 2.0 720pseedance-2.0-720p | $0.26 |
Seedance 2.0 Mini 720pseedance-2.0-mini-720p | $0.10 |
Seedance 2.5 1080pseedance-2.5-1080p | $0.48 |
Seedance 2.5 720pseedance-2.5-720p | $0.29 |
Seedance 2.5 720p Officialseedance-2.5-720p-official | $0.36 |
Veo 3.1veo-3.1720p/1080p | $0.08 |
| Veo 3.1, 4K | $0.12 |
Veo 3.1 Fastveo-3.1-fast720p/1080p | $0.03 |
| Veo 3.1 Fast, 4K | $0.07 |
Wan 3.0 1080pwan3.0-video-1080p | $0.33 |
Wan 3.0 Video Uncensoredwan-3.0-video-uncensoredUncensored480p | $0.40 |
| Wan 3.0 Video Uncensored, 720p | $0.80 |
| Wan 3.0 Video Uncensored, 1080p | $1.60 |
| Model | Rate |
|---|---|
Gemini 3 STTgemini-3-stt | $0.32 in $1.89 out per 1M tokens |
Gemini 3.1 TTSgemini-3.1-tts | $0.04 per request |
No model matches that search.
What will a request cost?
A text request costs its uncached input tokens times the input rate, plus cached input tokens times the cached rate, plus output tokens times the output rate, with each rate per 1M tokens.
For example, 10,000 input tokens and 2,000 output tokens on Claude Sonnet 5.5 cost about $0.0098, which is $0.0049 for input plus $0.0049 for output.
Estimates use the exact catalog rate. Cache-write charges, where a model has them, and Playground web search are not included.
How does Outrun billing work?
Outrun is prepaid. You add USD credit, and each request is charged from that balance for the tokens, images or seconds it used, at the rate on this page. There is no subscription or monthly fee.
- 01
Add credit
Top up with crypto or redeem a prepaid code in the Telegram bot. Eligible new accounts start with $0.10 in free credit, once per account, and abuse limits apply.
- 02
Pay per request
Text is charged per token, with separate input, cached input and output rates. Images are charged per image and video per second of output.
- 03
When credit runs out
Requests fail with an "Insufficient balance" error that shows what is left. Check with
/balancein the bot orGET /v1/account. - 04
Playground web search
10 free searches per account each day, then $0.0015 per successful search, with model tokens billed separately. Not part of the raw API.
Pricing questions
The billing guide covers top-ups, balances and errors in more detail.
Is every model cheaper on Outrun than the official API?
Not every one. The comparison table lists the 10 flagship models that cost 16% to 95% less on Outrun, with a link to each maker's price. Every other model is billed at the published rate in the full catalog.
What does Launch pricing mean?
Launch pricing marks an introductory Outrun rate on a recently added model. It can change, and this page always shows the rate that applies today.
How are prices rounded?
Tables show each rate rounded up to the cent. Charges use the exact rate and the token count of each request, so a small request can cost well under one cent.
Do cached tokens cost less?
Yes, on models that list a cached input rate. When a request reuses a prompt prefix that is already cached, those input tokens are charged at the cached rate in the catalog table.
Where do these prices come from?
Outrun rates come from the public catalog, also published as JSON at https://api.outrun.to/pricing. List prices were read from each model maker's own pricing page, and the comparison table links to each source.
$0.08lowest text input price per 1M tokens
Try any model at these prices.
Test a model in the Playground with your own credit, then connect your tools with the same key.